dev-reference
Skill2 starsChanged 2 months agoMITView on GitHub
Check actual tools, devices and environment before declaring access or a capability unavailable. Use before starting services or reporting an environment blocker.
In this repository5 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- briefSkill
- checkpointSkill
- client-feedbackSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 15
Read the full non-secret configuration relevant to the check.
- Distinctive: line 16
Never print credentials. Name the command, environment and exact limitation in a blocker report.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Verify the environment
| Need | Read-only starting check | What it does not prove |
| Tools | command -v <tool> and <tool> --version | An absent PATH entry is not a whole-machine search |
| iOS | xcrun simctl list devices | A simulator is not the reporting physical device |
| Android | adb devices and the configured SDK's emulator list | Empty connected devices does not mean no SDK |
| Local services | <health command> at the assigned port | Another process at that port is not your branch |
| Cloud | AWS_PROFILE=<profile> aws --region <region> sts get-caller-identity | Identity alone does not verify a resource or permission |
Read the full non-secret configuration relevant to the check; do not stop at the first page. Never print credentials. Name the command, environment and exact limitation in a blocker report.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.